unlearn-so_cifar10_resnet-50_neggrad_4_100 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_resnet-50_neggrad_4_100

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

100

This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:

Loss: -1.6751
Accuracy: 0.6604
Dt Accuracy: 0.6604
Df Accuracy: 0.661
Unlearn Overall Accuracy: 0.5375
Unlearn Time: None

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 128
eval_batch_size: 256
seed: 100
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	16	-0.1295	0.9755	0.2212	0.2212	None
No log	2.0	32	-0.1753	0.956	0.2511	0.2511	None
No log	3.0	48	-0.2886	0.921	0.3013	0.3013	None
No log	4.0	64	-0.5136	0.8735	0.3618	0.3618	None
No log	5.0	80	-0.7997	0.817	0.4242	0.4242	None
No log	6.0	96	-1.0981	0.764	0.4722	0.4722	None
No log	7.0	112	-1.3251	0.7215	0.5030	0.5030	None
No log	8.0	128	-1.5093	0.6925	0.5213	0.5213	None
No log	9.0	144	-1.6304	0.6705	0.5327	0.5327	None
No log	10.0	160	-1.6751	0.661	0.5375	0.5375	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2